Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add SethGammon/Citadel --skill designgit clone --depth 1 https://github.com/SethGammon/CitadelWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/sethgammon/citadel/design)<a href="https://agentmods.dev/skills/sethgammon/citadel/design"><img src="https://agentmods.dev/badge/skills/sethgammon/citadel/design/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sethgammon/citadel/design"><img src="https://agentmods.dev/badge/skills/sethgammon/citadel/design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00051 | $0.01537 |
| Opus 5.5 | $0.00020 | $0.00615 |
| Sonnet 5.5 | $0.00010 | $0.00307 |
| Haiku 4.5 | $0.00005 | $0.00154 |
Grade A, and why
design scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/design — Design Manifest Generator
When to Use
- At the start of a new project (generate starter manifest from preferences)
- On an existing project that has no manifest (extract patterns from existing code)
- When visual inconsistency is noticed ("why do we have 4 different button styles?")
- When /do routes "design", "style guide", "visual consistency", "design manifest"
Protocol
Step 1: DETECT MODE
Check for existing styles: look for tailwind.config.*, global CSS files, or component files with style patterns. If any exist, use Extract Mode. If none exist or the user says "new project", use Generate Mode.
Step 2: GATHER INPUT
Extract Mode: Read style sources (tailwind config, global CSS, component files). Present findings to user and confirm before writing.
Generate Mode: Ask up to 4 questions about feel, color mode, brand colors, and layout density. Use sensible defaults for anything not specified.
Step 3: WRITE MANIFEST
Write to .planning/design-manifest.md using the template defined below. Every section must have real values — no placeholders.
Step 4: CONFIRM
Present a summary of the manifest to the user: "Here's your design manifest. It will be used by the post-edit hook to flag deviations. Anything to change?"
Modes
Extract Mode (existing project has styles)
- Read
tailwind.config.*— extract colors, spacing, fonts, breakpoints - Read global CSS files — extract CSS variables, base styles
- Scan 5-10 component files — values used 3+ times become the palette, scale, type scale, shape language, and elevation scale; note component patterns (card, button, input)
- Present findings: "Here's what I found. Does this look right?"
- Write manifest after user confirms
Generate Mode (new project or no existing styles)
Ask up to 4 questions: feel (minimal/playful/corporate/bold), color mode (dark/light/both), brand colors (hex or "pick for me"), layout density. Use sensible defaults for anything not specified.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 182 lines · 51 tokens per session scan A ec0973ca024e
design is a skill published in the GitHub repository SethGammon/Citadel (925 stars, last pushed 2d ago), licensed MIT. It adds 51 tokens to every session and 1,537 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
prototype
Use when asked to prototype one design question through a cheap logic or UI experiment, including button-driven state-model checks. Not for polished artifacts: use polished-web-prototype.
humansense2system
Use when the user wants to compile taste and "this feels wrong" signals into machine-consumable tokens, rules, forbidden combinations, and examples. Elicits concrete cases, classifies each into one of four buckets, and writes a structured rule/pattern document. Not for remote, credential, publish, deploy, or…
fidelity-gate
Build a UI against a frozen visual reference without drift - an inventory extracted before any code, a relics list, and a gate that MEASURES computed styles on a fixture carrying the reference's own data. Use when a mockup, design spec or screenshot is the contract.
ux-grill
Use when a running web app's UX has to be audited reproducibly rather than by feel — a deterministic mechanical pass over routes and viewports (axe, target size, horizontal overflow, page title, scripted journeys) followed by a screenshot-grounded interrogation of the operator, journey by journey, with two persona…
typography-audit
Use when asked to audit typography across a codebase. Produces a file:line report with concrete fixes ordered by impact and flags unverifiable rules. Not for building a type system or token scale.
design
Use when starting UI work, defining palettes or tokens, fixing AI-generic UI, or persisting a design system to DESIGN.md (modes: implement, persist). Not for live URLs: use web-design-review.